Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/yokingma/weclawsnpx agentmods add skills/yokingma/weclaws/lark-baseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yokingma/weclaws/lark-base)<a href="https://agentmods.dev/skills/yokingma/weclaws/lark-base"><img src="https://agentmods.dev/badge/skills/yokingma/weclaws/lark-base/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yokingma/weclaws/lark-base"><img src="https://agentmods.dev/badge/skills/yokingma/weclaws/lark-base.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00116 | $0.09964 |
| Opus 5.5 | $0.00046 | $0.03986 |
| Sonnet 5.5 | $0.00023 | $0.01993 |
| Haiku 4.5 | $0.00012 | $0.00996 |
Grade A, and why
lark-base scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to lark-base — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
base
前置条件： 先阅读
../lark-shared/SKILL.md。 执行前必做： 执行任何base命令前，必须先阅读对应命令的 reference 文档，再调用命令。 查询类任务必做： 涉及筛选、排序、Top/Bottom N、聚合、多表关联、查询后写入或判断全局结论时，必须先阅读references/lark-base-data-analysis-sop.md，再选择record / view / data-query路径。 命名约定： Base 业务命令仅使用lark-cli base +...形式；如需先解析 Wiki 链接，可先调用lark-cli wiki ...。 分流规则： 如果用户要“把本地文件导入成 Base / 多维表格 / bitable”，第一步不是base，而是lark-cli drive +import --type bitable；导入完成后再回到lark-cli base +...做表内操作。
1. 何时使用本 Skill
1.1 触发条件
以下场景应使用本 skill：
- 用户明确要操作飞书多维表格 / Base。
- 用户要建表、改表、查表、删表，或管理字段、记录、视图。
- 用户要做公式字段、lookup 字段、派生指标、跨表计算。
- 用户要做临时统计、聚合分析、比较排序、求最值。
- 用户要管理 workflow、dashboard、表单、角色权限。
- 用户给出
/base/{token}链接。 - 用户给出
/wiki/{token}链接，且最终解析为bitable。 - 用户要把旧的 Base 聚合式写法改成当前原子命令写法，例如把旧
+table / +field / +record / +view / +history / +workspace改写成当前命令。
以下场景不应使用本 skill：
- 用户只是做认证、初始化配置、切换
--as user/bot、处理 scope。此时先读../lark-shared/SKILL.md。 - 用户只是泛化地讨论“数据分析 / 字段设计”，但并不在 Base 场景中。不要因为提到“统计 / 公式 / lookup”就误触发。
1.2 前置约束
- 先阅读
../lark-shared/SKILL.md。 - Base 业务命令仅使用
lark-cli base +...形式的 shortcut 命令；如果输入是 Wiki 链接，可先调用lark-cli wiki spaces get_node解析真实 token。 - 定位到命令后，先读该命令对应的 reference，再执行命令。
- 如果用户要把本地 Excel / CSV /
.base快照导入成 Base / 多维表格 / bitable，第一步不是base，而是lark-cli drive +import --type bitable；导入完成后再回到lark-cli base +...做表内操作。 - 不要在 Base 场景改走
lark-cli api /open-apis/bitable/v1/...。 - 如果用户只给 Base 名称、关键词，或说“帮我找一个多维表格”，先通过
lark-cli docs +search --query <keyword> --filter '{"doc_types":["BITABLE"]}'搜索BITABLE资源；拿到 Base URL 后再使用本 skill 的base +...命令。复杂搜索再读../lark-doc/references/lark-doc-search.md：标题精确匹配、限定创建者/群/文件夹/时间范围、只搜标题/评论、分页/全量搜索。
2. 模块与命令导航
本章按“先选模块，再选命令”的方式组织。先判断用户目标属于哪个大模块，再进入对应子模块，按要求阅读 reference 后执行命令。
2.1 模块地图
| 大模块 | 处理什么问题 | 包含的小模块 / 能力 |
|---|---|---|
| Base 模块 | 管理 Base 本体，或从链接进入 Base 场景 | base-create / base-get / base-copy，Base / Wiki 链接解析 |
| 表与数据模块 | 管理 Base 内部结构与日常数据操作 | table / field / record / view |
| 公式 / Lookup 模块 | 处理派生字段、条件判断、跨表计算、固定查找引用 | formula / lookup 字段创建与更新 |
| 数据分析模块 | 做一次性筛选、分组、聚合分析 | data-query |
| Workflow 模块 | 管理自动化流程 | workflow-list / get / create / update / enable / disable |
| Dashboard 模块 | 管理仪表盘和图表组件 | dashboard-* / dashboard-block-* |
| 表单模块 | 管理表单和表单题目 | form-* / form-questions-* |
| 权限与角色模块 | 管理高级权限和自定义角色 | advperm-* / role-* |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/dashboard-block-data-config.md 12 KB
- references/examples.md 3.1 KB
- references/formula-field-guide.md 54 KB
- references/lark-base-advperm-disable.md 2.1 KB
- references/lark-base-advperm-enable.md 2.0 KB
- references/lark-base-base-copy.md 2.7 KB
- references/lark-base-base-create.md 2.4 KB
- references/lark-base-base-get.md 975 B
- references/lark-base-cell-value.md 4.5 KB
- references/lark-base-dashboard-arrange.md 2.1 KB
- references/lark-base-dashboard-block-create.md 3.6 KB
- references/lark-base-dashboard-block-delete.md 1008 B
- references/lark-base-dashboard-block-get.md 1.7 KB
- references/lark-base-dashboard-block-list.md 1.5 KB
- references/lark-base-dashboard-block-update.md 3.0 KB
- references/lark-base-dashboard-create.md 1.7 KB
- references/lark-base-dashboard-delete.md 1.0 KB
- references/lark-base-dashboard-get.md 1.6 KB
- references/lark-base-dashboard-list.md 1.5 KB
- references/lark-base-dashboard-update.md 1.5 KB
- references/lark-base-dashboard.md 11 KB
- references/lark-base-data-analysis-sop.md 6.6 KB
- references/lark-base-data-query.md 19 KB
- references/lark-base-field-create.md 3.5 KB
- references/lark-base-field-delete.md 1.3 KB
- references/lark-base-field-get.md 904 B
- references/lark-base-field-list.md 992 B
- references/lark-base-field-search-options.md 1.2 KB
- references/lark-base-field-update.md 6.5 KB
- references/lark-base-field.md 1.3 KB
- references/lark-base-form-create.md 2.5 KB
- references/lark-base-form-delete.md 1.5 KB
- references/lark-base-form-get.md 1.6 KB
- references/lark-base-form-list.md 1.9 KB
- references/lark-base-form-questions-create.md 4.4 KB
- references/lark-base-form-questions-delete.md 1.8 KB
- references/lark-base-form-questions-list.md 2.0 KB
- references/lark-base-form-questions-update.md 2.8 KB
- references/lark-base-form-questions.md 1.0 KB
- references/lark-base-form-update.md 2.1 KB
- references/lark-base-form.md 1.0 KB
- references/lark-base-history.md 630 B
- references/lark-base-record-batch-create.md 2.1 KB
- references/lark-base-record-batch-update.md 2.1 KB
- references/lark-base-record-delete.md 1.8 KB
- references/lark-base-record-history-list.md 2.9 KB
- references/lark-base-record-share-link-create.md 1.9 KB
- references/lark-base-record-upload-attachment.md 1.6 KB
- references/lark-base-record-upsert.md 2.3 KB
- references/lark-base-record.md 2.6 KB
- references/lark-base-role-create.md 3.3 KB
- references/lark-base-role-delete.md 2.1 KB
- references/lark-base-role-get.md 2.7 KB
- references/lark-base-role-list.md 2.4 KB
- references/lark-base-role-update.md 2.8 KB
- references/lark-base-shortcut-field-properties.md 12 KB
- references/lark-base-table-create.md 1.7 KB
- references/lark-base-table-delete.md 1.3 KB
- references/lark-base-table-get.md 1.3 KB
- references/lark-base-table-list.md 948 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 350 lines · 116 tokens per session scan A 00c02ed5531c
lark-base is a skill published in the GitHub repository yokingma/weclaws (52 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 9,964 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to lark-base, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
sql-style
How to query the shop warehouse (tables, joins, date ranges).
migration-review
Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.
azure-resource-manager-mysql-dotnet
Azure MySQL Flexible Server SDK for .NET. Database management for MySQL Flexible Server deployments. Use for creating servers, databases, firewall rules, configurations, backups, and high availability. Triggers: "MySQL", "MySqlFlexibleServer", "MySQL Flexible Server", "Azure Database for MySQL", "MySQL database…
azure-resource-manager-postgresql-dotnet
Azure PostgreSQL Flexible Server SDK for .NET. Database management for PostgreSQL Flexible Server deployments. Use for creating servers, databases, firewall rules, configurations, backups, and high availability. Triggers: "PostgreSQL", "PostgreSqlFlexibleServer", "PostgreSQL Flexible Server", "Azure Database for…
wxjava-api-contributor
A contributor guide for adding or maintaining official WeChat API support in WxJava, a Java software development kit. It covers services, request and response data objects, data conversion, HTTP handling, starter configuration, and regression tests.
wxjava-troubleshooter
A troubleshooting guide for WxJava, a Java library used to connect applications to WeChat services. It organizes problems involving setup, access tokens, signatures, payment certificates, callbacks, data conversion, network requests, and multiple accounts.